USING NEURAL NETWORKS TO IMPROVE COMPUTATIONAL EFFICIENCY OF NUMERICAL MODELS

A new approach to improve computational efficiency of certain processes in numerical environmental models is formulated. This approach is based on the neural networks (NN) technique. The NN approach introduced here can provide numerically efficient solutions to a wide range of problems in numerical models where lengthy, complicated calculations, which describe physical processes, must be repeated frequently. Two particular applications of the NN approach are presented as illustrations of the approach: (1) a NN approximation of the UNESCO equation of state of the sea water (density of the seawater) and an inversion of this equation (salinity of the seawater); and (2) a NN approximation for the nonlinear wave-wave interaction. These applications belong to the field of oceanic and wave modeling; however, the method can be applied to efficiently calculate columnar physical processes (e.g., long- and short-wave radiation, convective physics, etc.) in atmospheric models as well. In environmental numerical models that incorporate chemical and biological components, this method can be applied to efficiently calculate chemical and biological processes as well. ~